AI Model Hub

Browse AI models for multimodal decomposition and recomposition pipelines — plug any model into your extractors.

14,077 models available

Get started Schedule Demo Read Documentation

Showing 8929–8952 of 14,077 models

Image Feature Extraction

MERaLiON/MERaLiON-SpeechEncoder-2

280

transformers

View Details

Summarization

sshleifer/distill-pegasus-cnn-16-4

279

transformers

View Details

Reinforcement Learning

Sudhish-Poojary/ppo-LunarLander-v3

279

stable-baselines3

View Details

Reinforcement Learning

SSGoatt/poca-SoccerTwos

279

ml-agents

View Details

Zero Shot Image Classification

wisdomik/QuiltNet-B-16

279

open_clip

View Details

Text To Video

suyehb/Wan2.2-TI2V-5B-GGUF

279

gguf

View Details

Question Answering

QuantFactory/SuperCorrect-7B-GGUF

279

transformers

View Details

Reinforcement Learning

HoaAn2003/ppo-Huggy

279

ml-agents

View Details

Summarization

mradermacher/amharic_summarization_mt5-GGUF

279

transformers

View Details

Text To Video

DuoNeural/Cosmos3-Nano-GPTQ-4bit

279

diffusers

View Details

Depth Estimation

Intel/zoedepth-kitti

278

transformers

View Details

Visual Question Answering

ybelkada/blip2-opt-2.7b-fp16-sharded

278

transformers

View Details

Audio Classification

THH0318/wav2vec2-base-finetuned-gtzan

278

transformers

View Details

Summarization

psyche/KoT5-summarization

278

transformers

View Details

Image To Text

docling-project/MarkushGrapher-2

278

transformers

View Details

Text To Audio

mimba/speecht5-ngiemboon

277

transformers

View Details

Robotics

chenpyyy/UD-VLA_CALVIN_ABCD_D

277

transformers

View Details

Question Answering

KoichiYasuoka/bert-base-japanese-wikipedia-ud-head

277

transformers

View Details

Audio Classification

ramen-noodels/red_round_button_small_click_detector_n75

277

transformers

View Details

Object Detection

merve/rfdetr-roadsign-agree2-large-noaug

277

transformers

View Details

Depth Estimation

qualcomm/Depth-Anything-V2

276

pytorch

View Details

Depth Estimation

romainhardy/ColonCrafter

276

transformers

View Details

Text To Audio

sil-ai/swh-bible-audio-speecht5

276

transformers

View Details

Document Question Answering

Xenova/donut-base-finetuned-docvqa

276

transformers.js

View Details

......

373 / 587

Connectors

Retrievers

What's new in models

Full changelog

Jun 22, 2026200+ model pages and new retrieval deep-divesExpanded the model catalog with enriched pages (architecture, benchmarks, Mixpeek SDK examples, and pipeline pairings) across embedding, vision-language, video, audio, OCR, and reranking models — plus new vendor-neutral guides on Matryoshka embeddings, reasoning rerankers, and retrieval feedback loops.